计算机工程与科学2025，Vol.47Issue(3)：494-503,10.DOI:10.3969/j.issn.1007-130X.2025.03.011
基于脉冲注意力机制的轻量化面部超分重建方法
A lightweight face super-resolution reconstruction method based on pulse attention mechanism
摘要
Abstract
Research on face super-resolution based on deep learning has made significant progress in recent years.However,a challenging aspect in this field is how to effectively restrict model complexity while preserving fine and natural facial textural details during the restoration process,and it's crucial to meet the demand of transferring the network model onto lightweight devices.Therefore,a lightweight face super-resolution reconstruction method based on pulse attention mechanism is proposed.The pro-posed new pulse attention mechanism integrates the multi-round global information extracted by the pulse-coupled neural network into the window self-attention mechanism,uses global information and lo-cal information to improve the learning ability of the network,and uses the adversarial generation net-work structure to build a progressive generator based on window self-attention to ensure the light-weighting of the method.Experimental results on the CelebA and Helen datasets show that this method performs excellently on LPIPS and MPS perceptual evaluation indicators.Compared with methods of the same parameter magnitude,it achieves significant improvement across all metrics and exhibits supe-rior subjective visual quality.关键词
人脸超分辨率/脉冲耦合神经网络/注意力机制/轻量化网络/生成对抗网络Key words
face super-resolution/pulse-coupled neural network/attention mechanism/lightweight network/generative adversarial network分类
信息技术与安全科学引用本文复制引用
李娇,高磊怡,张瑞欣,吴越,邓红霞..基于脉冲注意力机制的轻量化面部超分重建方法[J].计算机工程与科学,2025,47(3):494-503,10.基金项目
山西省中央引导地方科技发展资金(YDZJSX2022A016 （）
YDZJSX2021C005) （）
